Systems, methods, and other embodiments associated with a machine learning predictive model for predicting a propensity to implement energy reduction settings are described. Data records including load data for a target group of dwellings is obtained. An empirical load shape is generated for each given target dwelling based on the load data. A target feature vector is generated for each given target dwelling based on at least the empirical load shape corresponding to the given target dwelling. A trained machine learning predictive model is executed on the target feature vectors of the target group of dwellings to identify a set of target dwellings that are likely to reduce electricity consumed in accordance with electricity settings based on at least a generated predicted propensity for a target dwelling to implement the electricity settings.

A system and method for UAV power management includes a processor for monitoring power loads in the UAV and switching power sources based on a load profile in real time. The system may monitor flight phases or issued commands to proactively switch power sources in anticipation of an eminent change in the load profile.

A platform and components for an automated consumer retail utility marketplace are provided, including components for machine learning, components for gamification, and components for supporting a related consumer mobile application that enables improved visibility and control by a consumer over its interaction with energy markets.

A method of controlling a microgrid includes retrieving, by an energy management system, EMS, a forecast variable value for a forecast variable. The EMS determines an operating point value for a controllable asset that depends on the retrieved forecast variable value. The EMS determines an operating point shift value for the controllable asset, the operating point shift value representing a shift in operating point value in response to a variation in forecast variable value. The operating point value and the operating point shift value are provided to a power management system, PMS, of the microgrid.

According to some embodiments, system and method are provided comprising calculating an output power setpoint for a thermal generation system for a first calculation cycle of a time window having at least one calculation cycle; calculating a net demand for dispatchable power to satisfy a required load demand after calculating an available renewable power generation; determining, responsive to determining that the net demand for dispatchable power exceeds the output power setpoint for the thermal generation system, whether a discharge power of an energy storage device satisfies a power gap; generating, responsive to determining that the discharge power is not larger than a power rating, a discharge command to discharge the energy storage device at the discharge power; and increasing, responsive to determining that the discharge of the energy storage device fails to satisfy the power gap, the output power setpoint for the thermal generation system for the first calculation cycle.

An example operation includes one or more of determining, by a first energy source, that a second energy source configured to provide energy to an area is in need of supplemental energy, providing, by the first energy source, the supplemental energy to at least one location within the area in a prioritized manner, and responsive to a severity of the need and an amount of available energy at the first energy source, notifying, by the first energy source, the at least one transport to provide additional energy to the at least one location in the prioritized manner.

The present disclosure provides a distributed and anonymous approach to demand response of an electricity system. The approach conceptualizes energy consumption and production of distributed-energy resources (DERs) via discrete energy packets that are coordinated by a cyber computing entity that grants or denies energy packet requests from the DERs. The approach leverages a condition of a DER, which is particularly useful for (1) thermostatically-controlled loads, (2) non-thermostatic conditionally-controlled loads, and (3) bi-directional distributed energy storage systems. In a first aspect of the present approach, each DER independently requests the authority to switch on for a fixed amount of time (i.e., packet duration). The coordinator determines whether to grant or deny each request based electric grid and/or energy or power market conditions. In a second aspect, bi-directional DERs, such as distributed-energy storage systems (DESSs) are further able to request to supply energy to the grid.

An apparatus for monitoring an electrical apparatus, the load monitoring apparatus comprising a controller which is configured to capture and process voltage and current data of an electrical apparatus, which is electrically connected with a power supply, to obtain electrical parameters of the electrical apparatus, to store the electrical parameters as measured electrical parameters, to compare the measured electrical parameters with a set of pre-stored electrical parameters, to determine whether the measured electrical parameters match with the stored electrical parameters, and to operate a power switch to turn off power supply to the electrical parameters if the measured electrical parameters do not match with the stored electrical parameters.

A dynamic simulation engine, having system parameters, may be provided for a component of an electrical power system (e.g., a generator, wind turbine, etc.). A model parameter tuning engine may receive, from a measurement data store, measurement data measured by an electrical power system measurement unit (e.g., a phasor measurement unit or digital fault recorder measuring a disturbance event). The model parameter tuning engine may then pre-condition the measurement data and set-up an optimization problem based on a result of the pre-conditioning. The system parameters of the dynamic simulation engine may be determined by solving the optimization problem with an iterative method until at least one convergence criteria is met. According to some embodiments, solving the optimization problem includes a Jacobian approximation that does not call the dynamic simulation engine if an improvement of residual meets a pre-defined criteria.

A computing device includes a fuel price identifying unit that is configured to identify, based on a load plan and information on prediction of weather conditions, a fuel price in a case where motive power of a cooling water cooling device is varied, and a balance identifying unit that is configured to identify, based on the selling price of the generated electric power and the fuel price, at least a balance that is greater than a balance obtained by generated electric power according to the load plan in a case where a current operation is continued.